© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17323
    Prev
    Next
    INDEX
    Explanations

    disability and identity politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dissoci
    -0.11
    Behaviour
    -0.11
     behaviour
    -0.11
     foc
    -0.11
     Behaviour
    -0.11
     psychologically
    -0.10
     spontaneously
    -0.10
     objectively
    -0.10
     symbolism
    -0.10
    ingu
    -0.10
    POSITIVE LOGITS
     raced
    0.14
     histories
    0.11
     contest
    0.11
     formations
    0.11
     meanings
    0.11
     messy
    0.10
     fraught
    0.10
     contested
    0.10
     queer
    0.10
     ways
    0.10
    Activations Density 0.872%

    No Known Activations